INDEX

Explanations

instances of people and their roles or achievements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-0.68

KommentareTeilen

-0.65

 يتيمه

-0.63

jooq

-0.61

 незавершена

-0.60

Hentet

-0.60

SequentialGroup

-0.59

GOTREF

-0.57

nodoc

-0.56



-0.55

POSITIVE LOGITS

 participated

0.65

Particip

0.64

 proudest

0.62

 participate

0.62

 thường

0.61

 actively

0.61

 participates

0.60

 continued

0.59

 partici

0.59

 herum

0.59

Activations Density 0.161%

instances of people and their roles or achievements

No Comments

No Known Activations